CN110516077A - Knowledge mapping construction method and device towards enterprise's market conditions - Google Patents
Knowledge mapping construction method and device towards enterprise's market conditions Download PDFInfo
- Publication number
- CN110516077A CN110516077A CN201910767993.8A CN201910767993A CN110516077A CN 110516077 A CN110516077 A CN 110516077A CN 201910767993 A CN201910767993 A CN 201910767993A CN 110516077 A CN110516077 A CN 110516077A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- market conditions
- data
- event
- knowledge mapping
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/355—Class or cluster creation or modification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present invention provides a kind of knowledge mapping construction method and device towards enterprise's market conditions, wherein method includes: to obtain the market conditions data of enterprise inside and outside；According to the market conditions data of the enterprise inside and outside, utilize participle and name entity recognition techniques, the structural data for generating enterprise's market conditions includes the label of enterprise in the knowledge mapping towards enterprise's market conditions, mechanism, the correlating event of personage and event in the structural data of enterprise's market conditions；According to the structural data of enterprise's market conditions, the knowledge mapping towards enterprise's market conditions is constructed.The correlating event of enterprise, mechanism, personage can be integrated into enterprise's map by the embodiment of the present invention, the knowledge mapping towards enterprise's market conditions based on event be formed, effectively to realize the quick capture of market conditions event.
Description
Technical field
The present invention relates to technical field of data processing more particularly to a kind of knowledge mapping construction methods towards enterprise's market conditions
And device.
Background technique
In recent years, with the rapid development of information technology, skills such as big data, cloud computing and artificial intelligence in internet science and technology
The introducing and innovation of art, gradually in the high speed transition for leading finance and consumption industry.In information age today, the network media
Fast development, the importance of information assets more highlights, timely information processing and data-driven decision-making technic ability,
Gradually become enterprise core competence.
Knowledge presentation technology is an important component of artificial intelligence, and knowledge mapping is using the most wide representation of knowledge
One of method.Knowledge mapping is substantially semantic network, is a kind of data structure based on figure, and node represents entity
(entity) or concept (concept), the various semantic relations between Bian Daibiao entity/concept.Knowledge mapping can be used to more
Complicated related information is inquired well, understands that user is intended to from semantic level.
Because of the powerful semantic expressiveness ability of knowledge mapping, can be used for having contingency, the thing of variability using knowledge mapping
The expression of part, and the chance in market conditions event and risk have the characteristic of conduction, using traditional knowledge excavation mode
Through the quick capture that can not effectively realize market conditions event.
Summary of the invention
In view of the problems of the existing technology, the embodiment of the present invention provides a kind of knowledge mapping building towards enterprise's market conditions
Method and device.
The embodiment of the present invention provides a kind of knowledge mapping construction method towards enterprise's market conditions, comprising:
Obtain the market conditions data of enterprise inside and outside；
Enterprise's market conditions are generated using segmenting and naming entity recognition techniques according to the market conditions data of the enterprise inside and outside
Structural data, include enterprise in the knowledge mapping towards enterprise's market conditions, machine in the structural data of enterprise's market conditions
The label of structure, the correlating event of personage and event；
According to the structural data of enterprise's market conditions, the knowledge mapping towards enterprise's market conditions is constructed.
Optionally, the market conditions data of the enterprise inside and outside, comprising: enterprise's incidence relation data of enterprises and from mutual
The event data for the enterprise's market conditions obtained of networking；
Enterprise's incidence relation data of the enterprises, comprising: the enterprise investment relation data of enterprises, enterprise are high
Pipe incidence relation data and enterprise's upstream-downstream relationship data.
Optionally, the market conditions data according to the enterprise inside and outside, it is raw using participle and name entity recognition techniques
At the structural data of enterprise's market conditions, comprising:
Using preparatory trained Named Entity Extraction Model, in the event for extracting the market conditions data of the enterprise inside and outside
Entity, complete name Entity recognition；
The market conditions data of the enterprise inside and outside of completion name Entity recognition are taken out using the Named Entity Extraction Model
It takes and meets entity-predicate-entity structure sentence, frequency is obtained greater than default using the mode of Unsupervised clustering to predicate
Removed in acquired master-meaning-guest's member path according to cluster result without reality in master-meaning-guest's member path containing semanteme of threshold value
Remaining master-meaning-guest's member is had the predicate of business meaning to be converted between the guest that advocates peace by master-meaning of meaning-guest's member path in path
Incidence relation；
Using preparatory trained event tag output model, the quotient for completing the enterprise inside and outside of name Entity recognition is generated
The label of each event in feelings data.
Optionally, using preparatory trained Named Entity Extraction Model, the market conditions number of the enterprise inside and outside is extracted
According to event in entity, complete name Entity recognition before, the method also includes:
The event data for randomly selecting enterprise's market conditions of preset quantity, will be in the event data for the enterprise's market conditions that extracted
Sentence carries out participle and extracts Subject, Predicate and Object, the entity in the Subject, Predicate and Object is extracted, to the reality extracted by way of manually marking
Body carries out entity type mark, to obtain training sample；
In the way of supervised learning, the training sample is trained, generates trained name Entity recognition
Model.
Optionally, using preparatory trained event tag output model, the enterprise for completing name Entity recognition is generated
In the market conditions data of inside and outside before the label of each event, the method also includes:
For all kinds of event tag design systems in the event data of enterprise's market conditions, for each in the tag system
Label designs a model；
By way of manually marking, to all kinds of things in the market conditions data for the enterprise inside and outside for completing name Entity recognition
Part carries out label for labelling, to obtain mark sample；
It is embedded in word embedding deep learning technology using word, vector is carried out to the sentence in the mark sample and is turned
It changes, using the mode of supervised learning, the sentence after vector conversion is trained, generates event tag output model, it is described
Event tag output model is used for the label of outgoing event.
Optionally, in the structural data according to enterprise's market conditions, after constructing the knowledge mapping towards enterprise's market conditions,
The method also includes:
The knowledge mapping towards enterprise's market conditions of building is updated.
Optionally, in the structural data according to enterprise's market conditions, after constructing the knowledge mapping towards enterprise's market conditions,
The method also includes:
For the constructed knowledge mapping towards enterprise's market conditions, setting meets the rule of ontology schema schema, to from
Line batch data or real-time streaming data are handled, and the event that selection meets the rule is parsed and completes particular event
Automated tag marks work, and the offline batch data or real-time streaming data are the market conditions data of enterprise inside and outside.
The embodiment of the present invention provides a kind of knowledge mapping construction device towards enterprise's market conditions, comprising:
Module is obtained, for obtaining the market conditions data of enterprise inside and outside；
Generation module using participle and names entity recognition techniques for the market conditions data according to the enterprise inside and outside,
The structural data of enterprise's market conditions is generated, includes the knowledge mapping towards enterprise's market conditions in the structural data of enterprise's market conditions
In enterprise, mechanism, the correlating event of personage and event label；
Module is constructed, for the structural data according to enterprise's market conditions, constructs the knowledge mapping towards enterprise's market conditions.
The embodiment of the present invention provides a kind of electronic equipment, including memory, processor and storage are on a memory and can be
The computer program run on processor, the processor are realized when executing described program such as the step of the above method.
Knowledge mapping construction method and device provided in an embodiment of the present invention towards enterprise's market conditions, by obtaining in enterprise
External market conditions data generate enterprise quotient using segmenting and naming entity recognition techniques according to the market conditions data of enterprise inside and outside
The structural data of feelings, include in the structural data of enterprise's market conditions enterprise in the knowledge mapping towards enterprise's market conditions,
The label of mechanism, the correlating event of personage and event constructs knowing towards enterprise's market conditions according to the structural data of enterprise's market conditions
Know map, thereby, it is possible to which the correlating event of enterprise, mechanism, personage are integrated into enterprise's map, forms the face based on event
To the knowledge mapping of enterprise's market conditions, effectively to realize the quick capture of market conditions event.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of process signal for knowledge mapping construction method towards enterprise's market conditions that one embodiment of the invention provides
Figure；
Fig. 2 is a kind of structural representation for knowledge mapping construction device towards enterprise's market conditions that one embodiment of the invention provides
Figure；
Fig. 3 is the entity structure schematic diagram for the electronic equipment that one embodiment of the invention provides.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Fig. 1 shows a kind of process of knowledge mapping construction method towards enterprise's market conditions of one embodiment of the invention offer
Schematic diagram, as shown in Figure 1, the knowledge mapping construction method towards enterprise's market conditions of the present embodiment, comprising:
S1, the market conditions data for obtaining enterprise inside and outside.
It should be noted that the executing subject of the present embodiment the method is processor.
Wherein, the market conditions data of the enterprise inside and outside, may include: enterprises enterprise's incidence relation data and from
The event data for enterprise's market conditions that internet obtains；Enterprise's incidence relation data of the enterprises, may include: in enterprise
The relation datas such as enterprise investment relation data, top managers incidence relation data and enterprise's upstream-downstream relationship data in portion.
Specifically, the present embodiment can use internet crawler technology, (such as cut out to the relevant mainstream information website of enterprise
Sentence document net etc.) design crawler, realize the real-time acquisition of the event data of enterprise's market conditions, (such as using big data Computational frame
Spark & spark streaming frame), the title and article abstract of mainstream information website and webpage are parsed, as
The source of the event data of enterprise's market conditions of most original, mainly enterprise, mechanism, the news of personage and public sentiment data etc..This reality
The data source of enterprises integration can be accessed by applying example, obtain enterprise's incidence relation data of enterprises, also can use mutually
Networking crawler technology directly obtains industrial and commercial data on the net from national publicity, as enterprise's incidence relation data.
S2, enterprise quotient is generated using segmenting and naming entity recognition techniques according to the market conditions data of the enterprise inside and outside
The structural data of feelings, include in the structural data of enterprise's market conditions enterprise in the knowledge mapping towards enterprise's market conditions,
The label of mechanism, the correlating event of personage and event.
It is understood that the market conditions data that the present embodiment is the non-structured enterprise inside and outside that will acquire extract enterprise
Industry, mechanism, personage entity attribute and incidence relation, the label (institute based on enterprise, mechanism, the correlating event of personage and event
State tag representation entity attribute), generate the structural data of enterprise's market conditions.
S3, according to the structural data of enterprise's market conditions, construct the knowledge mapping towards enterprise's market conditions.
In a particular application, composition knowledge mapping main body can be completed according to the structural data of enterprise's market conditions
The storage and calculating of solid data, are realized using chart database, including automated data access, the functions such as data permission management are built
If knowledge mapping the build tool webprotege of open source then can be used, the building of knowledge mapping mode layer is completed.
It is understood that can also support to join after the completion of the knowledge mapping building towards enterprise's market conditions of the present embodiment
Machine function of search, intelligent answer function anticipate to the search problem or conversation sentence of user using natural language processing technique
Figure mapping, and it is converted into map query language, complete the Applications construct of the knowledge mapping towards enterprise's market conditions.This reality of later use
The knowledge mapping towards enterprise's market conditions for applying example building, can effectively realize the quick capture of market conditions event.
Knowledge mapping construction method provided in an embodiment of the present invention towards enterprise's market conditions, by obtaining enterprise inside and outside
Market conditions data generate the knot of enterprise's market conditions using segmenting and naming entity recognition techniques according to the market conditions data of enterprise inside and outside
Structure data include enterprise, mechanism, people in the knowledge mapping towards enterprise's market conditions in the structural data of enterprise's market conditions
The correlating event of object and the label of event construct the knowledge mapping towards enterprise's market conditions according to the structural data of enterprise's market conditions,
Thereby, it is possible to which the correlating event of enterprise, mechanism, personage are integrated into enterprise's map, formed based on event towards enterprise
The knowledge mapping of market conditions, effectively to realize the quick capture of market conditions event.
Further, on the basis of the above embodiments, the step S2 may include the step S21- being not shown in the figure
S23:
S21, using preparatory trained Named Entity Extraction Model, extract the thing of the market conditions data of the enterprise inside and outside
Entity in part completes name Entity recognition.
It is understood that the present embodiment can randomly select the thing of enterprise's market conditions of preset quantity before step S21
Sentence in the event data of the enterprise's market conditions extracted is carried out participle and extracts main (Subject) meaning by number of packages evidence
(Predicate) guest (Object) extracts the entity in the Subject, Predicate and Object, to the entity extracted by way of manually marking
Entity type mark is carried out, to obtain training sample；In the way of supervised learning, the training sample is trained,
Generate trained Named Entity Extraction Model.The trained Named Entity Extraction Model, for extracting the data of input
Event in entity, complete name Entity recognition.Wherein, entity type can exist according to the experience that knowledge mapping builds expert
It is set in schema.
It is understood that the present embodiment can extract enterprise, mechanism, personage in the market conditions data of enterprise inside and outside
Entity and entity attribute, complete name Entity recognition.
Enterprise that this step is extracted, mechanism, personage entity can with reference table 1, table 1 be the enterprise of citing a kind of, mechanism,
The entity table of personage.
Table 1
S22, the market conditions number using the Named Entity Extraction Model, to the enterprise inside and outside for completing name Entity recognition
According to extraction meets entity-predicate-entity structure sentence, and it is big using the mode of Unsupervised clustering to obtain frequency to predicate
It is gone in first path containing semantic master-meaning-guest (Subject-Predicate-Object) of preset threshold according to cluster result
Fall master-meaning without practical significance-guest's member path in acquired master-meaning-guest's member path, it will be in remaining master-meaning-guest's member path
There is the predicate of business meaning to be converted to the incidence relation between the guest that advocates peace.
It is understood that the present embodiment can extract the market conditions data for completing the enterprise inside and outside of name Entity recognition
In enterprise, mechanism, personage incidence relation, such as can refer to table 2, table 2 be the enterprise of citing a kind of, mechanism, personage pass
Join relation table.
Table 2
S23, preparatory trained event tag output model, the enterprise inside and outside of generation completion name Entity recognition are utilized
Market conditions data in each event label.
It is understood that the present embodiment can be for all kinds of in the event data of enterprise's market conditions before step S23
Event tag design system (the tag representation entity attribute in tag system) is designed for each label in the tag system
Model；By way of manually marking, to all kinds of events in the market conditions data for the enterprise inside and outside for completing name Entity recognition
Label for labelling is carried out, to obtain mark sample；Using word embedding (word insertion) deep learning technology, to the mark
Sentence in sample carries out vector conversion, using the mode of supervised learning, is trained, generates to the sentence after vector conversion
Event tag output model, the event tag output model are used for the label of outgoing event.By taking enterprise relates to the event of telling as an example, enterprise
Industry relates in the tag system (i.e. entity attribute) for the event of telling two important labels (index) and is whether enterprise responsible party and tells
Dispute event class, wherein whether responsible party is two classification problems for enterprise, contentious matter grade can be set to it is especially big, great,
It is great and four kinds general.
It is understood that the present embodiment can be generated in the market conditions data for completing the enterprise inside and outside of name Entity recognition
The label of each event.
Further, on the basis of the above embodiments, in the step S3 according to the structuring number of enterprise's market conditions
According to after constructing the knowledge mapping towards enterprise's market conditions, the present embodiment the method can also include:
The knowledge mapping towards enterprise's market conditions of building is updated.
It is understood that updating is database definition, operation, realized using chart database.
It is understood that the knowledge mapping towards enterprise's market conditions of the present embodiment building supports online updating, can obtain
The real-time market conditions data for taking enterprise inside and outside, real-time market conditions data based on acquired enterprise inside and outside, to building towards
The knowledge mapping of enterprise's market conditions is updated.
Further, on the basis of the above embodiments, in the step S3 according to the structuring number of enterprise's market conditions
According to after constructing the knowledge mapping towards enterprise's market conditions, the present embodiment the method can also include:
For the constructed knowledge mapping towards enterprise's market conditions, setting meets the rule of ontology schema (mode), right
Offline batch data or real-time streaming data are handled, and the event that selection meets the rule is parsed and completes particular event
Automated tag mark work, the offline batch data or real-time streaming data are the market conditions data of enterprise inside and outside.
It is understood that the present embodiment can be complete by open source Distributed Architecture, Message Queuing system and scheduling tool
At the Automation Construction of entire method flow, for example, can realize that the real-time streams of data are adopted by open source message queue kafka
Collection realizes knowledge mapping ontology management by open source knowledge mapping ontology construction tool webprotege, by control-M tune
Degree system realizes the operation automation of chart database and the regular push of labeled data using script.
It is understood that the framework of the knowledge mapping towards enterprise's market conditions constructed by the present embodiment can be divided into five
Layer: from the data active layer of bottom to the data product and application layer of top layer, middle layer includes data access layer, figure engine platform
With map management level；Wherein: data active layer can support a variety of data sources, including data source, enterprise external data in enterprise
Source etc., inside data of enterprise source may be from relevant database, distributed file system, data file etc., enterprise external number
According to may be from batch data file, internet interface etc., data content may include it is industrial and commercial, relate to tell, industrial chain, transaction etc. it is more
Dimension；Data access layer, that is, data administer platform, handle the data of data active layer, including data importing/export interface
And data processing tools, support accesses multiple data sources, Data Mining analysis, data cleansing and data simple analysis,
And then it generates the structural data of high quality or heterogeneous network data and exports, the input as figure engine platform；Figure engine is flat
Platform is the important foundation of map platform, can support that the data of isomery store and in addition computing platform is wrapped based on chart database
Relational database and artificial intelligence AI intelligent engine are included, realizes expression, storage, calculating of network data etc.；In figure engine platform
On the basis of plan map management level, realize the visualization building and data management of map, including map production management system and
Data platform dispatches system, and map production management system is used for the automated production and management of map, after being administered using data
Structural data or network data production map are simultaneously stored in chart database, and data platform dispatches system and is used to put down figure engine
The data of platform are managed collectively, the management functions such as the scheduling that fulfils assignment, message subscribing；It is data product on map management level
And application layer, the customer risk scoring obtained including client association map and model training center, transaction label product etc., with
Product form is supplied to application and development side or is supplied to business side directly as application and uses.
Knowledge mapping construction method provided in an embodiment of the present invention towards enterprise's market conditions, can be by enterprise, mechanism, personage
Correlating event be integrated into enterprise's map, form the knowledge mapping towards enterprise's market conditions based on event, from collection terminal to
Knowledge mapping application end can continue automatic operating after model and knowledge mapping are completed to build for the first time；The number that will be excavated
According in conjunction with user demand, intelligently being analyzed from semantic level, influence of the multi dimensional analysis market conditions event to enterprise；Map structure
After the completion of building, online searching function, intelligent answer function can be supported, the search using natural language processing technique, to user
Problem or conversation sentence carry out intention mapping, and are converted into map query language, that is, complete the Applications construct of map, utilize institute's structure
The knowledge mapping towards enterprise's market conditions built can effectively realize the quick capture of market conditions event.
Fig. 2 shows a kind of structures for knowledge mapping construction device towards enterprise's market conditions that one embodiment of the invention provides
Schematic diagram, as shown in Fig. 2, the knowledge mapping construction device towards enterprise's market conditions of the present embodiment, comprising: obtain module 21, life
At module 22 and building module 23；Wherein:
The acquisition module 21, for obtaining the market conditions data of enterprise inside and outside；
The generation module 22 is known for the market conditions data according to the enterprise inside and outside using participle and name entity
Other technology generates the structural data of enterprise's market conditions, includes towards enterprise's market conditions in the structural data of enterprise's market conditions
Enterprise, mechanism, the correlating event of personage and the label of event in knowledge mapping；
The building module 23 constructs knowing towards enterprise's market conditions for the structural data according to enterprise's market conditions
Know map.
Specifically, the market conditions data for obtaining module 21 and obtaining enterprise inside and outside；The generation module 22 is according to described
The market conditions data of enterprise inside and outside generate the structural data of enterprise's market conditions using segmenting and naming entity recognition techniques, described
Include in the structural data of enterprise's market conditions enterprise in the knowledge mapping towards enterprise's market conditions, mechanism, personage correlating event
And the label of event；The building module 23 constructs knowing towards enterprise's market conditions according to the structural data of enterprise's market conditions
Know map.
Wherein, the market conditions data of the enterprise inside and outside, may include: enterprises enterprise's incidence relation data and from
The event data for enterprise's market conditions that internet obtains；Enterprise's incidence relation data of the enterprises, may include: in enterprise
The relation datas such as enterprise investment relation data, top managers incidence relation data and enterprise's upstream-downstream relationship data in portion.
Specifically, the acquisition module 21 can use internet crawler technology, mainstream information website relevant to enterprise
(such as judgement document's net etc.) design crawler, realizes the real-time acquisition of the event data of enterprise's market conditions, utilizes big data calculation block
Frame (such as spark&spark streaming frame), parses the title and article abstract of mainstream information website and webpage, makees
For the source of the event data of enterprise's market conditions of most original, mainly enterprise, mechanism, the news of personage and public sentiment data etc..Institute
The data source of enterprises integration can be accessed by stating acquisition module 21, obtain enterprise's incidence relation data of enterprises, can also
Directly to obtain industrial and commercial data on the net from national publicity using internet crawler technology, as enterprise's incidence relation data.
It is understood that the market conditions data that the generation module 22 is the non-structured enterprise inside and outside that will acquire mention
Take enterprise, mechanism, personage entity attribute and incidence relation, the label based on enterprise, mechanism, the correlating event of personage and event
(the tag representation entity attribute) generates the structural data of enterprise's market conditions.
In a particular application, the building module 23 can complete composition according to the structural data of enterprise's market conditions
The storage and calculating of the solid data of knowledge mapping main body, are realized using chart database, including automated data access, data power
The Function Constructions such as limit management, then can be used knowledge mapping the build tool webprotege of open source, complete knowledge mapping mould
The building of formula layer.
It is understood that can also support to join after the completion of the knowledge mapping building towards enterprise's market conditions of the present embodiment
Machine function of search, intelligent answer function anticipate to the search problem or conversation sentence of user using natural language processing technique
Figure mapping, and it is converted into map query language, complete the Applications construct of the knowledge mapping towards enterprise's market conditions.This reality of later use
The knowledge mapping towards enterprise's market conditions for applying example building, can effectively realize the quick capture of market conditions event.
Knowledge mapping construction device provided in an embodiment of the present invention towards enterprise's market conditions, can be by enterprise, mechanism, personage
Correlating event be integrated into enterprise's map, the knowledge mapping towards enterprise's market conditions based on event is formed, effectively to realize
The quick capture of market conditions event.
Further, on the basis of the above embodiments, the generation module 22, can be specifically used for
Using preparatory trained Named Entity Extraction Model, in the event for extracting the market conditions data of the enterprise inside and outside
Entity, complete name Entity recognition；
The market conditions data of the enterprise inside and outside of completion name Entity recognition are taken out using the Named Entity Extraction Model
It takes and meets entity-predicate-entity structure sentence, frequency is obtained greater than default using the mode of Unsupervised clustering to predicate
Remove and obtained according to cluster result in first path containing semantic master-meaning-guest (Subject-Predicate-Object) of threshold value
Remaining master-meaning-guest's member is had business in path by master-meaning-guest's member path in the master-meaning taken-guest's member path without practical significance
The predicate of meaning is converted to the incidence relation between the guest that advocates peace；
Using preparatory trained event tag output model, the quotient for completing the enterprise inside and outside of name Entity recognition is generated
The label of each event in feelings data.
It is understood that the knowledge mapping construction device described in the present embodiment towards enterprise's market conditions can also include in figure
It is unshowned:
First training module, the event data of enterprise's market conditions for randomly selecting preset quantity, the enterprise that will be extracted
Sentence in the event data of market conditions carries out participle extraction main (Subject) and calls (Predicate) guest (Object), described in extraction
Entity in Subject, Predicate and Object carries out entity type mark to the entity extracted by way of manually marking, to obtain trained sample
This；In the way of supervised learning, the training sample is trained, generates trained Named Entity Extraction Model.
The trained Named Entity Extraction Model, the entity in event for extracting the data inputted are completed name entity and are known
Not.Wherein, entity type can be set in schema according to the experience that knowledge mapping builds expert.
It is understood that the knowledge mapping construction device described in the present embodiment towards enterprise's market conditions can also include in figure
It is unshowned:
Second training module, for for all kinds of event tag design system (labels in the event data of enterprise's market conditions
Tag representation entity attribute in system), it designs a model for each label in the tag system；Pass through the side manually marked
Formula carries out label for labelling to all kinds of events in the market conditions data for the enterprise inside and outside for completing name Entity recognition, to obtain mark
Infuse sample；Using word embedding (word insertion) deep learning technology, vector is carried out to the sentence in the mark sample
Conversion is trained the sentence after vector conversion, is generated event tag output model, institute using the mode of supervised learning
State label of the event tag output model for outgoing event.By taking enterprise relates to the event of telling as an example, enterprise relates to the label system for the event of telling
Two important labels (index) in (i.e. entity attribute) of uniting be enterprise whether responsible party and contentious matter grade, wherein enterprise
Whether responsible party is two classification problems to industry, and contentious matter grade can be set to especially big, great, great and four kinds general.
In this way, the present embodiment can be realized the market conditions data according to the enterprise inside and outside, participle and name entity are utilized
Identification technology generates the structural data of enterprise's market conditions.
Further, on the basis of the above embodiments, the knowledge mapping building described in the present embodiment towards enterprise's market conditions
Device can also include not shown in the figure:
Update module, for being updated to the knowledge mapping towards enterprise's market conditions of building.
It is understood that updating is database definition, operation, realized using chart database.
It is understood that the knowledge mapping towards enterprise's market conditions of the present embodiment building supports online updating, can obtain
The real-time market conditions data for taking enterprise inside and outside, real-time market conditions data based on acquired enterprise inside and outside, to building towards
The knowledge mapping of enterprise's market conditions is updated.
Further, on the basis of the above embodiments, the knowledge mapping building described in the present embodiment towards enterprise's market conditions
Device can also include not shown in the figure:
Processing module, for being directed to the constructed knowledge mapping towards enterprise's market conditions, setting meets ontology schema (mould
Formula) rule, offline batch data or real-time streaming data are handled, selection meets the event of the rule and parsed simultaneously
The automated tag for completing particular event marks work, and the offline batch data or real-time streaming data are the quotient of enterprise inside and outside
Feelings data.
It is understood that the present embodiment can be complete by open source Distributed Architecture, Message Queuing system and scheduling tool
At the Automation Construction for the process that whole device module executes, for example, can realize data by open source message queue kafka
Real-time streams acquisition realizes knowledge mapping ontology management by open source knowledge mapping ontology construction tool webprotege, by
Control-M is dispatched system and is realized the operation automation of chart database and the regular push of labeled data using script.
It is understood that the framework of the knowledge mapping towards enterprise's market conditions constructed by the present embodiment can be divided into five
Layer: from the data active layer of bottom to the data product and application layer of top layer, middle layer includes data access layer, figure engine platform
With map management level；Wherein: data active layer can support a variety of data sources, including data source, enterprise external data in enterprise
Source etc., inside data of enterprise source may be from relevant database, distributed file system, data file etc., enterprise external number
According to may be from batch data file, internet interface etc., data content may include it is industrial and commercial, relate to tell, industrial chain, transaction etc. it is more
Dimension；Data access layer, that is, data administer platform, handle the data of data active layer, including data importing/export interface
And data processing tools, support accesses multiple data sources, Data Mining analysis, data cleansing and data simple analysis,
And then it generates the structural data of high quality or heterogeneous network data and exports, the input as figure engine platform；Figure engine is flat
Platform is the important foundation of map platform, can support that the data of isomery store and in addition computing platform is wrapped based on chart database
Relational database and artificial intelligence AI intelligent engine are included, realizes expression, storage, calculating of network data etc.；In figure engine platform
On the basis of plan map management level, realize the visualization building and data management of map, including map production management system and
Data platform dispatches system, and map production management system is used for the automated production and management of map, after being administered using data
Structural data or network data production map are simultaneously stored in chart database, and data platform dispatches system and is used to put down figure engine
The data of platform are managed collectively, the management functions such as the scheduling that fulfils assignment, message subscribing；It is data product on map management level
And application layer, the customer risk scoring obtained including client association map and model training center, transaction label product etc., with
Product form is supplied to application and development side or is supplied to business side directly as application and uses.
Knowledge mapping construction device provided in an embodiment of the present invention towards enterprise's market conditions, can be by enterprise, mechanism, personage
Correlating event be integrated into enterprise's map, form the knowledge mapping towards enterprise's market conditions based on event, from collection terminal to
Knowledge mapping application end can continue automatic operating after model and knowledge mapping are completed to build for the first time；The number that will be excavated
According in conjunction with user demand, intelligently being analyzed from semantic level, influence of the multi dimensional analysis market conditions event to enterprise；Map structure
After the completion of building, online searching function, intelligent answer function can be supported, the search using natural language processing technique, to user
Problem or conversation sentence carry out intention mapping, and are converted into map query language, that is, complete the Applications construct of map, utilize institute's structure
The knowledge mapping towards enterprise's market conditions built can effectively realize the quick capture of market conditions event.
Knowledge mapping construction device provided in an embodiment of the present invention towards enterprise's market conditions, can be used for executing preceding method
The technical solution of embodiment, it is similar that the realization principle and technical effect are similar, and details are not described herein again.
Fig. 3 shows the entity structure schematic diagram of a kind of electronic equipment of one embodiment of the invention offer, as shown in figure 3,
The electronic equipment may include memory 302, processor 301, bus 303 and be stored on memory 302 and can be in processor
The computer program run on 301, wherein processor 301, memory 302 complete mutual communication by bus 303.Institute
State the step of realizing the above method when processor 301 executes the computer program, for example, obtain the quotient of enterprise inside and outside
Feelings data；Enterprise's market conditions are generated using segmenting and naming entity recognition techniques according to the market conditions data of the enterprise inside and outside
Structural data, include in the structural data of enterprise's market conditions enterprise in the knowledge mapping towards enterprise's market conditions, mechanism,
The correlating event of personage and the label of event；According to the structural data of enterprise's market conditions, knowing towards enterprise's market conditions is constructed
Know map.
The embodiment of the present invention provides a kind of non-transient computer readable storage medium, is stored thereon with computer program, should
The step of above method is realized when computer program is executed by processor, for example, obtain the market conditions data of enterprise inside and outside；
The structuring of enterprise's market conditions is generated using segmenting and naming entity recognition techniques according to the market conditions data of the enterprise inside and outside
Data include enterprise, mechanism, personage in the knowledge mapping towards enterprise's market conditions in the structural data of enterprise's market conditions
The label of correlating event and event；According to the structural data of enterprise's market conditions, the knowledge mapping towards enterprise's market conditions is constructed.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (10)
1. a kind of knowledge mapping construction method towards enterprise's market conditions characterized by comprising
Obtain the market conditions data of enterprise inside and outside；
The knot of enterprise's market conditions is generated using segmenting and naming entity recognition techniques according to the market conditions data of the enterprise inside and outside
Structure data include enterprise, mechanism, people in the knowledge mapping towards enterprise's market conditions in the structural data of enterprise's market conditions
The correlating event of object and the label of event；
According to the structural data of enterprise's market conditions, the knowledge mapping towards enterprise's market conditions is constructed.
2. the knowledge mapping construction method according to claim 1 towards enterprise's market conditions, which is characterized in that in the enterprise
External market conditions data, comprising: the event of enterprise's incidence relation data of enterprises and the enterprise's market conditions obtained from internet
Data；
Enterprise's incidence relation data of the enterprises, comprising: enterprise investment relation data, the top managers of enterprises close
Join relation data and enterprise's upstream-downstream relationship data.
3. the knowledge mapping construction method according to claim 1 towards enterprise's market conditions, which is characterized in that described according to institute
The market conditions data for stating enterprise inside and outside generate the structural data of enterprise's market conditions, packet using segmenting and naming entity recognition techniques
It includes:
Using preparatory trained Named Entity Extraction Model, the reality in the event of the market conditions data of the enterprise inside and outside is extracted
Body completes name Entity recognition；
The market conditions data of the enterprise inside and outside of completion name Entity recognition are extracted full using the Named Entity Extraction Model
Full body-predicate-entity structure sentence obtains frequency greater than preset threshold using the mode of Unsupervised clustering to predicate
Containing semantic master-meaning-guest's member path, according to cluster result, remove in acquired master-meaning-guest's member path without practical significance
Master-meaning-guest's member path, there is the predicate of business meaning to be converted to the pass between the guest that advocates peace in path remaining master-meaning-guest's member
Connection relationship；
Using preparatory trained event tag output model, the market conditions number for completing the enterprise inside and outside of name Entity recognition is generated
The label of each event in.
4. the knowledge mapping construction method according to claim 3 towards enterprise's market conditions, which is characterized in that using in advance
Trained Named Entity Extraction Model extracts the entity in the event of the market conditions data of the enterprise inside and outside, completes name
Before Entity recognition, the method also includes:
The event data for randomly selecting enterprise's market conditions of preset quantity, by the sentence in the event data of the enterprise's market conditions extracted
Carry out participle extract Subject, Predicate and Object, extract the entity in the Subject, Predicate and Object, by way of manually marking to the entity extracted into
Row entity type mark, to obtain training sample；
In the way of supervised learning, the training sample is trained, generates trained Named Entity Extraction Model.
5. the knowledge mapping construction method according to claim 3 towards enterprise's market conditions, which is characterized in that using in advance
Trained event tag output model generates each event in the market conditions data for completing the enterprise inside and outside of name Entity recognition
Before label, the method also includes:
For all kinds of event tag design systems in the event data of enterprise's market conditions, for each label in the tag system
It designs a model；
By way of manually marking, to complete name Entity recognition enterprise inside and outside market conditions data in all kinds of events into
Row label mark, to obtain mark sample；
It is embedded in word embedding deep learning technology using word, vector conversion is carried out to the sentence in the mark sample,
Using the mode of supervised learning, the sentence after vector conversion is trained, event tag output model, the event are generated
Label output model is used for the label of outgoing event.
6. the knowledge mapping construction method according to claim 1 towards enterprise's market conditions, which is characterized in that according to
The structural data of enterprise's market conditions, after constructing the knowledge mapping towards enterprise's market conditions, the method also includes:
The knowledge mapping towards enterprise's market conditions of building is updated.
7. the knowledge mapping construction method according to claim 1 towards enterprise's market conditions, which is characterized in that according to
The structural data of enterprise's market conditions, after constructing the knowledge mapping towards enterprise's market conditions, the method also includes:
For the constructed knowledge mapping towards enterprise's market conditions, setting meets the rule of ontology schema schema, to offline batch
Amount data or real-time streaming data are handled, and the event that selection meets the rule is parsed and completes the automatic of particular event
Label for labelling work, the offline batch data or real-time streaming data are the market conditions data of enterprise inside and outside.
8. a kind of knowledge mapping construction device towards enterprise's market conditions characterized by comprising
Module is obtained, for obtaining the market conditions data of enterprise inside and outside；
Generation module is generated for the market conditions data according to the enterprise inside and outside using segmenting and naming entity recognition techniques
The structural data of enterprise's market conditions includes in the knowledge mapping towards enterprise's market conditions in the structural data of enterprise's market conditions
The label of enterprise, mechanism, the correlating event of personage and event；
Module is constructed, for the structural data according to enterprise's market conditions, constructs the knowledge mapping towards enterprise's market conditions.
9. a kind of electronic equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor is realized when executing described program such as any one of claim 1 to 7 the method
Step.
10. a kind of non-transient computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer
It is realized when program is executed by processor such as the step of any one of claim 1 to 7 the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910767993.8A CN110516077A (en) | 2019-08-20 | 2019-08-20 | Knowledge mapping construction method and device towards enterprise's market conditions |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910767993.8A CN110516077A (en) | 2019-08-20 | 2019-08-20 | Knowledge mapping construction method and device towards enterprise's market conditions |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110516077A true CN110516077A (en) | 2019-11-29 |
Family
ID=68625823
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910767993.8A Pending CN110516077A (en) | 2019-08-20 | 2019-08-20 | Knowledge mapping construction method and device towards enterprise's market conditions |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110516077A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111160847A (en) * | 2019-12-09 | 2020-05-15 | 中国建设银行股份有限公司 | Method and device for processing flow information |
| CN111400504A (en) * | 2020-03-12 | 2020-07-10 | 支付宝(杭州)信息技术有限公司 | Method and device for identifying enterprise key people |
| CN111414485A (en) * | 2020-03-17 | 2020-07-14 | 北京恒通慧源大数据技术有限公司 | Enterprise customer association relation map construction method and device, storage and computer |
| CN111598461A (en) * | 2020-05-19 | 2020-08-28 | 北京海致星图科技有限公司 | Enterprise knowledge graph-based real-time risk generalization and conduction analysis method |
| CN112085104A (en) * | 2020-09-10 | 2020-12-15 | 杭州中奥科技有限公司 | Event feature extraction method and device, storage medium and electronic equipment |
| CN112084335A (en) * | 2020-09-09 | 2020-12-15 | 电子科技大学 | Social media user account classification method based on information fusion |
| CN112131275A (en) * | 2020-09-23 | 2020-12-25 | 中国科学技术大学智慧城市研究院(芜湖) | Enterprise portrait construction method of holographic city big data model and knowledge graph |
| CN112149422A (en) * | 2020-09-23 | 2020-12-29 | 中冶赛迪工程技术股份有限公司 | Enterprise news dynamic monitoring method based on natural language |
| CN112214611A (en) * | 2020-09-24 | 2021-01-12 | 远光软件股份有限公司 | Construction system and method of enterprise knowledge graph |
| CN112241401A (en) * | 2020-10-16 | 2021-01-19 | 中国民用航空华东地区空中交通管理局 | Knowledge graph-based digital quality management system and method |
| CN112330183A (en) * | 2020-11-18 | 2021-02-05 | 布瑞克农业大数据科技集团有限公司 | Method and system for constructing big data portrait of agricultural enterprise |
| CN112529308A (en) * | 2020-12-16 | 2021-03-19 | 平安国际智慧城市科技股份有限公司 | Event prediction method, device and storage medium |
| CN113688254A (en) * | 2021-08-25 | 2021-11-23 | 中国民用航空飞行学院 | Construction method of aviation dynamic information structured data model |
| WO2021254457A1 (en) * | 2020-06-17 | 2021-12-23 | 第四范式（北京）技术有限公司 | Method and device for constructing knowledge graph, computer device, and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060071060A (en) * | 2004-12-21 | 2006-06-26 | 함덕환 | Administrative affairs integration management system |
| CN106447346A (en) * | 2016-08-29 | 2017-02-22 | 北京中电普华信息技术有限公司 | Method and system for construction of intelligent electric power customer service system |
| CN106815293A (en) * | 2016-12-08 | 2017-06-09 | 中国电子科技集团公司第三十二研究所 | System and method for constructing knowledge graph for information analysis |
| CN108182295A (en) * | 2018-02-09 | 2018-06-19 | 重庆誉存大数据科技有限公司 | A kind of Company Knowledge collection of illustrative plates attribute extraction method and system |
-
2019
- 2019-08-20 CN CN201910767993.8A patent/CN110516077A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060071060A (en) * | 2004-12-21 | 2006-06-26 | 함덕환 | Administrative affairs integration management system |
| CN106447346A (en) * | 2016-08-29 | 2017-02-22 | 北京中电普华信息技术有限公司 | Method and system for construction of intelligent electric power customer service system |
| CN106815293A (en) * | 2016-12-08 | 2017-06-09 | 中国电子科技集团公司第三十二研究所 | System and method for constructing knowledge graph for information analysis |
| CN108182295A (en) * | 2018-02-09 | 2018-06-19 | 重庆誉存大数据科技有限公司 | A kind of Company Knowledge collection of illustrative plates attribute extraction method and system |
Non-Patent Citations (1)
| Title |
|---|
| 程文亮: ""中文企业知识图谱构建与分析"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111160847B (en) * | 2019-12-09 | 2023-08-25 | 中国建设银行股份有限公司 | Method and device for processing flow information |
| CN111160847A (en) * | 2019-12-09 | 2020-05-15 | 中国建设银行股份有限公司 | Method and device for processing flow information |
| CN111400504A (en) * | 2020-03-12 | 2020-07-10 | 支付宝(杭州)信息技术有限公司 | Method and device for identifying enterprise key people |
| CN111400504B (en) * | 2020-03-12 | 2023-04-07 | 支付宝(杭州)信息技术有限公司 | Method and device for identifying enterprise key people |
| CN111414485A (en) * | 2020-03-17 | 2020-07-14 | 北京恒通慧源大数据技术有限公司 | Enterprise customer association relation map construction method and device, storage and computer |
| CN111414485B (en) * | 2020-03-17 | 2022-09-30 | 北京恒通慧源大数据技术有限公司 | Enterprise customer association relationship map construction method and device, storage and computer |
| CN111598461A (en) * | 2020-05-19 | 2020-08-28 | 北京海致星图科技有限公司 | Enterprise knowledge graph-based real-time risk generalization and conduction analysis method |
| WO2021254457A1 (en) * | 2020-06-17 | 2021-12-23 | 第四范式（北京）技术有限公司 | Method and device for constructing knowledge graph, computer device, and storage medium |
| CN112084335A (en) * | 2020-09-09 | 2020-12-15 | 电子科技大学 | Social media user account classification method based on information fusion |
| CN112085104A (en) * | 2020-09-10 | 2020-12-15 | 杭州中奥科技有限公司 | Event feature extraction method and device, storage medium and electronic equipment |
| CN112085104B (en) * | 2020-09-10 | 2024-04-12 | 杭州中奥科技有限公司 | Event feature extraction method and device, storage medium and electronic equipment |
| CN112149422A (en) * | 2020-09-23 | 2020-12-29 | 中冶赛迪工程技术股份有限公司 | Enterprise news dynamic monitoring method based on natural language |
| CN112131275A (en) * | 2020-09-23 | 2020-12-25 | 中国科学技术大学智慧城市研究院(芜湖) | Enterprise portrait construction method of holographic city big data model and knowledge graph |
| CN112149422B (en) * | 2020-09-23 | 2024-04-05 | 中冶赛迪工程技术股份有限公司 | Dynamic enterprise news monitoring method based on natural language |
| CN112214611A (en) * | 2020-09-24 | 2021-01-12 | 远光软件股份有限公司 | Construction system and method of enterprise knowledge graph |
| CN112214611B (en) * | 2020-09-24 | 2023-10-31 | 远光软件股份有限公司 | Enterprise knowledge graph construction system and method |
| CN112241401A (en) * | 2020-10-16 | 2021-01-19 | 中国民用航空华东地区空中交通管理局 | Knowledge graph-based digital quality management system and method |
| CN112330183A (en) * | 2020-11-18 | 2021-02-05 | 布瑞克农业大数据科技集团有限公司 | Method and system for constructing big data portrait of agricultural enterprise |
| CN112529308A (en) * | 2020-12-16 | 2021-03-19 | 平安国际智慧城市科技股份有限公司 | Event prediction method, device and storage medium |
| CN113688254A (en) * | 2021-08-25 | 2021-11-23 | 中国民用航空飞行学院 | Construction method of aviation dynamic information structured data model |
| CN113688254B (en) * | 2021-08-25 | 2023-06-02 | 中国民用航空飞行学院 | Construction method of aviation dynamic information structured data model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110516077A (en) | Knowledge mapping construction method and device towards enterprise's market conditions | |
| Bharadiya | A comparative study of business intelligence and artificial intelligence with big data analytics | |
| CN111428053B (en) | Construction method of tax field-oriented knowledge graph | |
| CN107766371B (en) | Text information classification method and device | |
| CN108491378B (en) | Intelligent response system for operation and maintenance of electric power information | |
| CN110807091A (en) | Hotel intelligent question-answer recommendation and decision support analysis method and system | |
| CN108874783A (en) | Power information O&M knowledge model construction method | |
| CN107368521B (en) | Knowledge recommendation method and system based on big data and deep learning | |
| CN115002200B (en) | Message pushing method, device, equipment and storage medium based on user portrait | |
| CN109389423A (en) | A kind of marketing application method based on big data fusion business | |
| CN110321549B (en) | New concept mining method based on sequential learning, relation mining and time sequence analysis | |
| CN112580332B (en) | Enterprise portrait method based on label layering and deepening modeling | |
| CN116468460B (en) | Consumer finance customer image recognition system and method based on artificial intelligence | |
| Das et al. | A CV parser model using entity extraction process and big data tools | |
| CN109992704A (en) | A kind of enterprise's public sentiment monitoring system and method based on shot and long term Memory Neural Networks | |
| CN116501779A (en) | Big data mining analysis system for real-time feedback | |
| CN113379432B (en) | Sales system customer matching method based on machine learning | |
| Kim et al. | Customer preference analysis based on SNS data | |
| CN113344604B (en) | User subdivision method based on user behavior data and stream calculation | |
| CN106407271B (en) | Intelligent customer service system and updating method of intelligent customer service knowledge base thereof | |
| CN115099680A (en) | Risk management method, device, equipment and storage medium | |
| Sui et al. | [Retracted] Optimization Simulation of Supply‐Side Structure of Agricultural Economy Based on Big Data Analysis in Data Sharing Environment | |
| CN114780744A (en) | Figure resume analysis method for knowledge graph construction | |
| KR20230059364A (en) | Public opinion poll system using language model and method thereof | |
| Alazeb et al. | Review on data science and prediction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191129 |
|
| RJ01 | Rejection of invention patent application after publication |